{
  "name": "io.github.mem0ai/mem0",
  "description": "The Mem0 MCP gives an AI agent a managed memory layer that survives across sessions and conversations. The agent stores facts, preferences, and context with a single tool call; on the next conversation, the MCP retrieves the right slices semantically. Unlike a raw vector store, Mem0 does the summarisation, deduplication, and decay automatically — closer to \"human memory\" than \"embedding index.\"",
  "status": "active",
  "version": "latest",
  "_meta": {
    "com.top-mcps/lastVerified": "2026-06-02",
    "com.top-mcps/score": {
      "value": 98,
      "rubricVersion": "2026-04",
      "lastComputed": "2026-06-02T13:16:41.658Z",
      "methodology": "https://top-mcps.com/about/methodology"
    },
    "com.top-mcps/stats": {
      "fetchedAt": "2026-06-02T13:16:41.411Z",
      "githubStars": 57390,
      "lastCommitAt": "2026-06-01T20:18:36Z"
    }
  },
  "repository": {
    "url": "https://github.com/mem0ai/mem0",
    "source": "github"
  },
  "author": {
    "name": "Mem0"
  },
  "packages": [
    {
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org",
      "identifier": "run",
      "version": "latest",
      "transport": {
        "type": "stdio"
      },
      "runtimeArguments": [
        {
          "type": "positional",
          "value": "--rm"
        },
        {
          "type": "positional",
          "value": "-i"
        },
        {
          "type": "positional",
          "value": "-e"
        },
        {
          "type": "positional",
          "value": "MEM0_API_KEY"
        },
        {
          "type": "positional",
          "value": "mem0ai/mem0-mcp:latest"
        }
      ],
      "environmentVariables": [
        {
          "name": "MEM0_API_KEY",
          "description": "MEM0_API_KEY — required credential for Mem0.",
          "isRequired": true,
          "isSecret": true
        },
        {
          "name": "MEM0_USER_ID",
          "description": "MEM0_USER_ID — required credential for Mem0.",
          "isRequired": true,
          "isSecret": true
        }
      ]
    }
  ],
  "capabilities": {
    "tools": [
      {
        "name": "add_memory",
        "description": "Store a piece of context against a user.",
        "sideEffect": "write",
        "args": [
          {
            "name": "content",
            "type": "string",
            "required": true
          },
          {
            "name": "user_id",
            "type": "string",
            "required": true
          }
        ]
      },
      {
        "name": "search_memory",
        "description": "Semantically retrieve relevant memories for a user.",
        "sideEffect": "read",
        "args": [
          {
            "name": "query",
            "type": "string",
            "required": true
          },
          {
            "name": "user_id",
            "type": "string",
            "required": true
          }
        ]
      },
      {
        "name": "list_memories",
        "description": "List all memories for a user.",
        "sideEffect": "read",
        "args": [
          {
            "name": "user_id",
            "type": "string",
            "required": true
          }
        ]
      },
      {
        "name": "delete_memory",
        "description": "Delete a specific memory.",
        "sideEffect": "write",
        "args": [
          {
            "name": "memory_id",
            "type": "string",
            "required": true
          }
        ]
      }
    ],
    "security": {
      "scope": "read-write",
      "sandbox": "Cloud mode talks to api.mem0.ai with an API key scoped to one workspace. Self-hosted mode talks to a local server you operate; memories never leave the host.",
      "gotchas": [
        "API keys carry full workspace access — rotate on any team change.",
        "user_id must be set per-conversation; without it, memories pool into a shared bucket and leak across users.",
        "Mem0 stores embeddings of your raw turns — review your privacy contract before sending PII into it."
      ]
    }
  },
  "_links": {
    "html": "https://top-mcps.com/mcp/mem0",
    "markdown": "https://top-mcps.com/mcp/mem0.md",
    "methodology": "https://top-mcps.com/about/methodology"
  }
}
